Joint inference of entities, relations, and coreference

Authors:
Sameer Singh;Sebastian Riedel;Brian Martin;Jiaping Zheng;Andrew McCallum
Affiliations:
University of Massachusetts, Amherst, MA, USA;University College London, London, United Kingdom;University of Massachusetts, Amherst, MA, USA;University of Massachusetts, Amherst, MA, USA;University of Massachusetts, Amherst, MA, USA
Venue:
Proceedings of the 2013 workshop on Automated knowledge base construction
Year:
2013

Citing 27
Cited 0

A machine learning approach to coreference resolution of noun phrases

Computational Linguistics - Special issue on computational anaphora resolution
An integrated, conditional model of information extraction and coreference with application to citation matching

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Improving machine learning approaches to coreference resolution

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Introduction to the CoNLL-2003 shared task: language-independent named entity recognition

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Maximum entropy models for named entity recognition

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Exploring various knowledge in relation extraction

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Exploring syntactic features for relation extraction using a convolution tree kernel

HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Linear Programming Relaxations and Belief Propagation -- An Empirical Study

The Journal of Machine Learning Research
The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies

CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Design challenges and misconceptions in named entity recognition

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning
Solving the problem of cascading errors: approximate Bayesian inference for linguistic annotation pipelines

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Understanding the value of features for coreference resolution

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Bi-directional Joint Inference for Entity Resolution and Segmentation Using Imperatively-Defined Factor Graphs

ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II
Joint inference in information extraction

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Joint parsing and named entity recognition

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
A machine learning approach to building domain-specific search engines

IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
Piecewise training for structured prediction

Machine Learning
Simple coreference resolution with rich syntactic and semantic features

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3
Joint parsing and semantic role labeling

CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
Coreference resolution in a modular, entity-centered model

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Joint inference for knowledge extraction from biomedical literature

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Joint entity and relation extraction using card-pyramid parsing

CoNLL '10 Proceedings of the Fourteenth Conference on Computational Natural Language Learning
Collective cross-document relation extraction without labelled data

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Jointly identifying entities and extracting relations in encyclopedia text via a graphical model approach

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Semi-supervised relation extraction with large-scale word clustering

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Fast and robust joint models for biomedical event extraction

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Factor graphs and the sum-product algorithm

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Although joint inference is an effective approach to avoid cascading of errors when inferring multiple natural language tasks, its application to information extraction has been limited to modeling only two tasks at a time, leading to modest improvements. In this paper, we focus on the three crucial tasks of automated extraction pipelines: entity tagging, relation extraction, and coreference. We propose a single, joint graphical model that represents the various dependencies between the tasks, allowing flow of uncertainty across task boundaries. Since the resulting model has a high tree-width and contains a large number of variables, we present a novel extension to belief propagation that sparsifies the domains of variables during inference. Experimental results show that our joint model consistently improves results on all three tasks as we represent more dependencies. In particular, our joint model obtains 12% error reduction on tagging over the isolated models.